A.I.
Fintech Enterprise SaaS
Zero → One
Company: FloQast
AI-Powered solution to a tedious accounting process
Problem
Each month, accountants face significant challenges in reconciling and matching their Intercompany transactions, often encountering errors and inefficiencies.
Solution
Leverage AI to automate the burdensome task of reconciliation. prioritizing trust and reliability.
Result
Decreased manual effort and errors. As a SaaS company, we signed 10 clients in first 3 months.
.png)
Context
FloQast is an accounting workflow management system for small to enterprise accounting teams, looking to expand to Intercompany Reconciliations as part of the monthly Close process.
Every month, accounting teams ‘close the books,’ a critical process that includes reconciling transactions conducted between different parts of the same company—known as Intercompany Reconciliation. This is often a time-consuming and complex task that clearly demands automation.
Challenge
The core challenge lies in developing an effective and scalable solution to automate the matching component of the reconciliation process—reducing the need for manual intervention, increasing accuracy, and enabling greater efficiency across workflows.
Strategy: Goals & Vision
Business Opportunity
Our goal is to streamline and accelerate the reconciliation process, not only to make the module more appealing to potential new customers but also to enhance its value for existing clients—creating meaningful opportunities for upselling and deeper product adoption.
Product Vision
Intercompany AI Matching is built on the principle that accountants should transition from being preparers to becoming reviewers. Our goal was to design a product that automates the tedious, time-consuming, and error-prone aspects of reconciliation, enabling accountants to dedicate more time to strategic, high-value activities."
Team Collaboration
As the senior product designer, I worked closely with the Product Manager, Engineering Lead, and development team to ensure we were addressing the right problems and prioritizing features and user flows that would deliver the greatest impact.
Design Principles
My focus centered on the principles of trust, scalability, and cognitive ease. Interacting with an AI tool should be intuitive and straightforward. Every feature was thoughtfully designed to simplify the reconciliation process, ensuring we meet both user needs and business objectives.
User Needs
We conducted interviews with 12 companies, including several who served as design partners— and uncovered the biggest struggles and frustrations they face when attempting Intercompany reconciliation.
Users need to complete intercompany matching faster to allow them to shift their attention away from repetitive and manual work and focus instead on more strategic, high-level responsibilities.
- Reconciliation remains a consistently challenging and time-consuming process.
- It is often prone to human error due to manual inputs and fragmented data sources, making it difficult for users to trust the accuracy of the results.
- The lack of a centralized view makes it hard to grasp the full picture or identify patterns.
Solution
The goal was to leverage AI to automate the burdensome task of reconciliation—elevating accountants from preparers to reviewers—while accelerating the process. At the same time, we prioritized trust and reliability by building a solution that includes audit capabilities to support thorough review and accountability.
Ideation
Opportunities
To support ideation, I reformulated the key pain points into 'How Might We' statements.
- HMW provide an AI matching experience that's SCALABLE?
- HMW promote trust and auditability of the rules and subsequent matches so that users feel confident in the results?
- HMW empower users with a holistic view, enabling them to identify trends and prioritize high-impact actions?
Prioritization
For the MVP, our primary goal was to deliver a functional rule builder that could operate across entity relationships. After launch, we planned to iterate with larger feature sets, a more scalable UI, and potentially explore alternative ways to author rules.
Design concepting
I began with a user flow, making sure I covered all steps in the process.I began with wireframes and converted to higher fidelity when I validated the concepts with internal stakeholders as well as potential clients.
Usability testing
We tested the designs, both as a prototype and in code, with client design partners. Their feedback was instrumental in shaping the product.
Findings:
1) Users want to see number of matches
2) An audit log of when new transactions were added
3) Users need a way to unmatch
Findings:
1) Users want to see number of matches
2) An audit log of when new transactions were added
3) Users need a way to unmatch
Feature
AI Rule Builder
User Problem
“I need to view the transactions as I create AI rules, so I have the context necessary to write them accurately.”
Solution
Rather than using a modal or slide-out drawer, we opted for a layout that shifts the content to the side—allowing users to view and interact with both sections simultaneously.
.png)
Feature
AI Rule Card
User Problem
I need a way to see all rules, where they are applied, and any change in activity for auditability.
Solution
A module solution that presents AI-matched transactions in a clear, reviewable format—shifting the role of accountants from preparers to reviewers.
.png)
Feature
Settings
User Problem
“I want to stay focused on what truly matters—anything below a certain threshold shouldn’t distract or clutter the experience.”
Solution
Materiality Settings empower users to define precisely what information they want to focus on—and filter out what they don't.
Feature
Global Views
User Problem
"I want a high-level view that shows where the problems are and what's performing well."
Solution
The matrix view, alongside the list view, acts like a heat map—surfacing key problem areas at a glance.
Impact
Intercompany AI Matching was positively received by Beta participants, with several companies choosing to sign on specifically because of its capabilities. A cohort of accounting experts offered strong praise for its functionality and impact. As a result, we successfully met our business objective of cutting down manual effort, driving adoption and delivering meaningful value to our target audience.
Retro
Tradeoffs
We’ve chosen not to implement the audit log for the MVP, as user feedback indicated it’s not a critical feature for initial adoption.
Working with Engineering
I maintained ongoing collaboration with the engineering team to understand the limitations of the AI and to adjust the design solution accordingly.
Next Steps
We plan to continue expanding the feature set and enhancing the platform's capabilities, with a strong focus on scalability to meet the needs of enterprise-level customers.
Working with Design Systems
I leveraged existing design system components and consulted with fellow designers to identify any established patterns. Additionally, I developed new design patterns where gaps were identified to ensure a cohesive and effective user experience.
Learnings
- When designing for scale, solutions must accommodate varying use cases and a breadth of data.
- Incorporating AI requires a close, ongoing collaboration with engineering teams to ensure technical feasibility and that performance aligns with the user experience.
- Users consistently emphasize the need for trust and transparency in AI-driven systems, highlighting the importance of auditability.